watch_sceen_ai

Files

EJClaw 0e77f659d5 perf(brain): shorter, faster voice replies (max_tokens 400->150, brevity prompt, cache)

Voice replies were too long and slow (~1.3s LLM). Cap output at 150 tokens
(WSAI_BRAIN_MAX_TOKENS), rewrite the persona to demand one short sentence with
no boilerplate self-intro / "무엇을 도와드릴까요" padding, and mark the static
system prompt with cache_control so repeat turns skip re-processing it.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-08-27 01:36:35 +09:00

backends

perf(brain): shorter, faster voice replies (max_tokens 400->150, brevity prompt, cache)

2026-08-27 01:36:35 +09:00

__init__.py

feat: scaffold watch-screen AI pipeline (mock-runnable skeleton)

2026-08-09 02:16:14 +09:00

__main__.py

feat(dashboard): 4-way roster (user/bot/voice/role), persistence, TTS all-emotions, layout

2026-08-27 00:14:24 +09:00

bot_control.py

feat(dashboard): 4-way roster (user/bot/voice/role), persistence, TTS all-emotions, layout